Univariate analysis of variance is generally inappropriate when there are three or more measures per S. A few simple precautions concerning the appropriate use of multivariate and univariate analysis are given.
Get full access to this article
View all access options for this article.
References
1.
AndersonT. W.Introduction to multivariate statistical analysis. New York: Wiley, 1958.
2.
BoxG. E. P.Effects of inequality of variance and correlation between errors in the two-way classification. Ann. math. Statist., 1954, 25, 584–598.
3.
GeisserS.GreenhouseS. W.An extension of Box's results on the use of the F distribution in multivariate analysis. Ann. math. Statist., 1958, 29, 885–891.
4.
HotellingH.The generalization of ‘Student's ratio.’Ann. math. Statist., 1931, 2, 360–378.
5.
JonckheereA. R.A test of significance for the relations between m rankings and k ranked categories. Brit. J. statist. Psychol., 1954, 7, 93–100.
